Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1611 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.1307. Min Act: -0.1700

Data Index: 402989 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.0682. Min Act: -0.1700

Data Index: 434794 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.0057. Min Act: -0.1700

Data Index: 1046988 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9745. Min Act: -0.1700

Data Index: 275256 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9745. Min Act: -0.1700

Data Index: 64962 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9432. Min Act: -0.1700

Data Index: 879489 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9120. Min Act: -0.1700

Data Index: 585802 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8807. Min Act: -0.1700

Data Index: 51383 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9432. Min Act: -0.1700

Data Index: 80490 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8807. Min Act: -0.1700

Data Index: 553929 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 1145623 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8807. Min Act: -0.1700

Data Index: 457506 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 46578 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9120. Min Act: -0.1700

Data Index: 293013 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 123032 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8182. Min Act: -0.1700

Data Index: 726128 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 388900 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 773422 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8495. Min Act: -0.1700

Data Index: 740227 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.7870. Min Act: -0.1700

Data Index: 478028 (C4 (Web Text))

Max Activating Token Index: 606